Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313495212> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4313495212 endingPage "11" @default.
- W4313495212 startingPage "1" @default.
- W4313495212 abstract "Convolutional neural networks, as most artificial neural networks, are frequently viewed as methods different in essence from kernel-based methods. In this work we translate several classical convolutional neural networks into kernel-based counterparts. Each kernel-based counterpart is a statistical model called a convolutional kernel network with parameters that can be learned from data. We provide an alternating minimization algorithm with mini-batch sampling and implicit partial differentiation to learn from data the parameters of each convolutional kernel network. We also show how to obtain inexact derivatives with respect to the parameters using an algorithm based on two inter-twined Newton iterations. The models and the algorithms are illustrated on benchmark datasets in image classification. We find that the convolutional neural networks and their kernel counterparts often perform similarly. Supplemental appendices and code for the article are available online." @default.
- W4313495212 created "2023-01-06" @default.
- W4313495212 creator A5010613767 @default.
- W4313495212 creator A5046132757 @default.
- W4313495212 creator A5047279709 @default.
- W4313495212 date "2023-02-16" @default.
- W4313495212 modified "2023-10-01" @default.
- W4313495212 title "Revisiting Convolutional Neural Networks from the Viewpoint of Kernel-Based Methods" @default.
- W4313495212 cites W1483804921 @default.
- W4313495212 cites W1502922572 @default.
- W4313495212 cites W1567512734 @default.
- W4313495212 cites W1826072219 @default.
- W4313495212 cites W1985242550 @default.
- W4313495212 cites W1993105114 @default.
- W4313495212 cites W2010315761 @default.
- W4313495212 cites W2051434435 @default.
- W4313495212 cites W2101926813 @default.
- W4313495212 cites W2116360511 @default.
- W4313495212 cites W2558748708 @default.
- W4313495212 cites W2943191253 @default.
- W4313495212 cites W3118114660 @default.
- W4313495212 cites W4298876635 @default.
- W4313495212 doi "https://doi.org/10.1080/10618600.2022.2163649" @default.
- W4313495212 hasPublicationYear "2023" @default.
- W4313495212 type Work @default.
- W4313495212 citedByCount "0" @default.
- W4313495212 crossrefType "journal-article" @default.
- W4313495212 hasAuthorship W4313495212A5010613767 @default.
- W4313495212 hasAuthorship W4313495212A5046132757 @default.
- W4313495212 hasAuthorship W4313495212A5047279709 @default.
- W4313495212 hasBestOaLocation W43134952122 @default.
- W4313495212 hasConcept C114614502 @default.
- W4313495212 hasConcept C119857082 @default.
- W4313495212 hasConcept C153180895 @default.
- W4313495212 hasConcept C154945302 @default.
- W4313495212 hasConcept C33923547 @default.
- W4313495212 hasConcept C41008148 @default.
- W4313495212 hasConcept C74193536 @default.
- W4313495212 hasConcept C81363708 @default.
- W4313495212 hasConceptScore W4313495212C114614502 @default.
- W4313495212 hasConceptScore W4313495212C119857082 @default.
- W4313495212 hasConceptScore W4313495212C153180895 @default.
- W4313495212 hasConceptScore W4313495212C154945302 @default.
- W4313495212 hasConceptScore W4313495212C33923547 @default.
- W4313495212 hasConceptScore W4313495212C41008148 @default.
- W4313495212 hasConceptScore W4313495212C74193536 @default.
- W4313495212 hasConceptScore W4313495212C81363708 @default.
- W4313495212 hasFunder F4320320373 @default.
- W4313495212 hasLocation W43134952121 @default.
- W4313495212 hasLocation W43134952122 @default.
- W4313495212 hasOpenAccess W4313495212 @default.
- W4313495212 hasPrimaryLocation W43134952121 @default.
- W4313495212 hasRelatedWork W2175746458 @default.
- W4313495212 hasRelatedWork W2613736958 @default.
- W4313495212 hasRelatedWork W2732542196 @default.
- W4313495212 hasRelatedWork W2738221750 @default.
- W4313495212 hasRelatedWork W2760085659 @default.
- W4313495212 hasRelatedWork W3012978760 @default.
- W4313495212 hasRelatedWork W3027997911 @default.
- W4313495212 hasRelatedWork W3081496756 @default.
- W4313495212 hasRelatedWork W3093612317 @default.
- W4313495212 hasRelatedWork W4287776258 @default.
- W4313495212 isParatext "false" @default.
- W4313495212 isRetracted "false" @default.
- W4313495212 workType "article" @default.